AI agents use launch_create to create or update resources in Testops — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Testops environment.
The tool creates a new test run/launch in the TestOps system. This is a reversible write operation — new data is created but can presumably be deleted or stopped later (sibling tool 'launch_stop' exists). No destructive, financial, or execution side effects are described.
From the tool's definition 'Create a test run (launch). Body requires name and projectId.' — creates a new resource (test launch) with no indication of irreversibility or financial impact.
Attacks that exploit this kind of access
Create a test run (launch). Body requires name and projectId. It is categorised as a Write tool in the Testops MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Testops MCP server in PolicyLayer and add a rule for launch_create: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Testops. Nothing to install.
launch_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the launch_create rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for launch_create. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
launch_create is provided by the Testops MCP server (@syn7xx/testops-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →